基于神经网络的烈度衰减融合模型研究  

Research on Fusion Model of Seismic Intensity Attenuation Based on Neural Network

作　　者：胡旺[1] 张建[1] 陈维锋[2] 胡斌[2] 郭红梅[2] 

机构地区：[1]电子科技大学计算机科学与工程学院,成都611731 [2]四川省地震局,成都610041

出　　处：《电子科技大学学报》2018年第2期224-229,共6页Journal of University of Electronic Science and Technology of China

基　　金：国家科技支撑计划(2015BAK18B03-01);四川省科技支撑计划(2015FZ0043;2016GZ0077);贵州省科技支撑计划(黔科合[2016]支撑2810)

摘　　要：地震烈度衰减关系一直以来都是地震领域的研究热点和难点。不同学者建立了各地区的地震烈度衰减关系模型,并取得较好的应用效果。为了进一步提高地震烈度衰减模型预测的准确性,该文收集了川滇地区107个地震案例共243条地震等震线,利用BP神经网络对基于传统模型的中国西部烈度衰减关系和基于矩阵模型的烈度衰减关系的预测结果进行了学习融合,得到了川滇地区的融合预测模型。仿真结果表明,融合预测模型的预测准确性总体上优于中国西部烈度衰减关系和矩阵衰减关系。It is the hotpot and challenge in the field of earthquake for charactering seismic intensityattenuation relationship. Many scholars have established some prediction models of seismic intensity attenuation.In order to further improve the prediction accuracy of the seismic intensity attenuation models, 243 isoseismicsfrom 107 earthquake cases are collected from Sichuan-Yunnan to establish a new comprehensive prediction modelbase on back propagation （BP） neural network. This prediction model fuses the merits of the Western Chinaintensity attenuation relation based on the traditional model and the matrix attenuation relation based on matrixmodel. The experimental result shows that the prediction accuracy of the proposed fusion model is better than thatof the matrix attenuation relationship and the western Chinese intensity attenuation relationship.

关 键 词：人工神经网络 融合预测模型 烈度衰减模型 地震影响场 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]